{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2TSHH6GYRFXJV6FUZNXLWXGBIG","short_pith_number":"pith:2TSHH6GY","schema_version":"1.0","canonical_sha256":"d4e473f8d8896e9af8b4cb6ebb5cc141a10975cf1eb26ea3fef211d6d437ba28","source":{"kind":"arxiv","id":"2308.06160","version":2},"attestation_state":"computed","paper":{"title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hong Zhou, Mike Zheng Shou, Rui Zhao, Weijia Wu, Yefei He, Yuchao Gu, Yuzhong Zhao","submitted_at":"2023-08-11T14:38:11Z","abstract_excerpt":"Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.06160","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-11T14:38:11Z","cross_cats_sorted":[],"title_canon_sha256":"d44d60d9c4f0c05b9605b793ee3205bc94484d020f26e0eb8abd3b2bc3ed76f0","abstract_canon_sha256":"9132778b2621f5f487f6423ae57da6aacddd1e8a7f932ea6556857ecd9a566a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:58.930441Z","signature_b64":"M2e3oMkWf/RkCq6JvSo1Yhs2mIFYzJzzrAhe3FxCpmgsZeH4IX3TRfE4OjbNNo+gaeJgu/tX7V8mgJVaT/yTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e473f8d8896e9af8b4cb6ebb5cc141a10975cf1eb26ea3fef211d6d437ba28","last_reissued_at":"2026-07-05T06:58:58.930024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:58.930024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hong Zhou, Mike Zheng Shou, Rui Zhao, Weijia Wu, Yefei He, Yuchao Gu, Yuzhong Zhao","submitted_at":"2023-08-11T14:38:11Z","abstract_excerpt":"Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06160","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.06160/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.06160","created_at":"2026-07-05T06:58:58.930079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06160v2","created_at":"2026-07-05T06:58:58.930079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06160","created_at":"2026-07-05T06:58:58.930079+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TSHH6GYRFXJ","created_at":"2026-07-05T06:58:58.930079+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TSHH6GYRFXJV6FU","created_at":"2026-07-05T06:58:58.930079+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TSHH6GY","created_at":"2026-07-05T06:58:58.930079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02217","citing_title":"Understanding Trade offs When Conditioning Synthetic Data","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG","json":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG.json","graph_json":"https://pith.science/api/pith-number/2TSHH6GYRFXJV6FUZNXLWXGBIG/graph.json","events_json":"https://pith.science/api/pith-number/2TSHH6GYRFXJV6FUZNXLWXGBIG/events.json","paper":"https://pith.science/paper/2TSHH6GY"},"agent_actions":{"view_html":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG","download_json":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG.json","view_paper":"https://pith.science/paper/2TSHH6GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06160&json=true","fetch_graph":"https://pith.science/api/pith-number/2TSHH6GYRFXJV6FUZNXLWXGBIG/graph.json","fetch_events":"https://pith.science/api/pith-number/2TSHH6GYRFXJV6FUZNXLWXGBIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG/action/storage_attestation","attest_author":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG/action/author_attestation","sign_citation":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG/action/citation_signature","submit_replication":"https://pith.science/pith/2TSHH6GYRFXJV6FUZNXLWXGBIG/action/replication_record"}},"created_at":"2026-07-05T06:58:58.930079+00:00","updated_at":"2026-07-05T06:58:58.930079+00:00"}